FileMaker 2026: AI Gets Serious

Claris FileMaker 2026 (v26) brings major AI upgrades including Google Gemini support, smarter schema annotations for LLMs, and a roadmap toward fully agentic FileMaker development.

Claris officially released FileMaker 2026 (internal version 26) in June 2026, and it's the most AI-forward release in the platform's 40-year history.

What's New for AI & LLMs

Google Gemini support
FileMaker now supports Google Gemini alongside existing providers — OpenAI, Anthropic (Claude), and Cohere. Gemini also allows developers to pass container-field images directly into prompts for visual analysis workflows.

Field & Table Annotations
A long-standing frustration has been solved: you can now add a dedicated field annotation via the Database Manager's Advanced options. This gives LLMs proper context about what a field means — not just what it's named. The new FieldAnnotation() and BaseTableComment() calculation functions make this metadata accessible at runtime too.

Faster JSON & API calls
When Insert from URL retrieves a JSON response, it is now automatically parsed and cached — making all subsequent JSON operations dramatically faster. A major win for solutions that make heavy use of REST APIs and AI calls.

AI Model Server improvements
The AI Model Server now has its own version number and can be upgraded independently of FileMaker Server. Multiple Python processes mean embedding and text-generation workloads run concurrently rather than queuing.

Timeout control
Text generation steps now accept a CURLOPT_TIMEOUT parameter in seconds — so if a local/open-source model server stalls, your scripts no longer hang indefinitely.

What's Coming: Agentic FileMaker Development

The bigger news may be what's next. Claris CEO Ryan McCann has outlined a vision for agentic coding capabilities — where tools like Claude Code, Cursor, and Codex can read your FileMaker schema and automatically generate native scripts, tables, fields, layouts, and calculations.

Developer previews are expected later this summer (2026).

Why This Matters for Your FileMaker Solutions

You can now connect FileMaker to multiple AI providers and choose based on cost, capability, or data residency requirements.
Schema annotations make natural language queries and semantic search significantly more accurate — without restructuring your database.
Local LLM support remains fully intact: run models like Llama 3 on-premise, keeping sensitive data entirely within your own infrastructure.

FileMaker 2026 treats AI as a foundational platform layer, not an add-on — and the agentic capabilities coming this summer could fundamentally change how FileMaker solutions are built.